SOTAVerified

Imitation Learning

Imitation Learning is a framework for learning a behavior policy from demonstrations. Usually, demonstrations are presented in the form of state-action trajectories, with each pair indicating the action to take at the state being visited. In order to learn the behavior policy, the demonstrated actions are usually utilized in two ways. The first, known as Behavior Cloning (BC), treats the action as the target label for each state, and then learns a generalized mapping from states to actions in a supervised manner. Another way, known as Inverse Reinforcement Learning (IRL), views the demonstrated actions as a sequence of decisions, and aims at finding a reward/cost function under which the demonstrated decisions are optimal.

Finally, a newer methodology, Inverse Q-Learning aims at directly learning Q-functions from expert data, implicitly representing rewards, under which the optimal policy can be given as a Boltzmann distribution similar to soft Q-learning

Source: Learning to Imitate

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 726–750 of 2122 papers

TitleStatusHype
Informed Sampling for Diversity in Concept-to-Text NLG—0
GymFG: A Framework with a Gym Interface for FlightGear—0
Generating stable molecules using imitation and reinforcement learning—0
Auto-Encoding Inverse Reinforcement Learning—0
A Statistical Guarantee for Representation Transfer in Multitask Imitation Learning—0
Generative Adversarial Imitation Learning with Neural Networks: Global Optimality and Convergence Rate—0
Generative Adversarial Imitation Learning with Neural Network Parameterization: Global Optimality and Convergence Rate—0
Generative Adversarial Imitation Learning for Empathy-based AI—0
Generative Adversarial Imitation Learning for End-to-End Autonomous Driving on Urban Environments—0
Action-Free Reasoning for Policy Generalization—0
Exploration Based Language Learning for Text-Based Games—0
Explaining Imitation Learning through Frames—0
Generative predecessor models for sample-efficient imitation learning—0
Generic Oracles for Structured Prediction—0
Genetic Imitation Learning by Reward Extrapolation—0
GenH2R: Learning Generalizable Human-to-Robot Handover via Scalable Simulation, Demonstration, and Imitation—0
GenH2R: Learning Generalizable Human-to-Robot Handover via Scalable Simulation Demonstration and Imitation—0
CodeDiffuser: Attention-Enhanced Diffusion Policy via VLM-Generated Code for Instruction Ambiguity—0
Gesture2Path: Imitation Learning for Gesture-aware Navigation—0
Get Back Here: Robust Imitation by Return-to-Distribution Planning—0
GHIL-Glue: Hierarchical Control with Filtered Subgoal Images—0
CMR-Agent: Learning a Cross-Modal Agent for Iterative Image-to-Point Cloud Registration—0
H2O: A Benchmark for Visual Human-human Object Handover Analysis—0
Global Reinforcement Learning: Beyond Linear and Convex Rewards via Submodular Semi-gradient Methods—0
Explaining Fast Improvement in Online Imitation Learning—0
Show:102550
← PrevPage 30 of 85Next →

No leaderboard results yet.